Land suitability analysis using geographic information systems (GIS) is one of the most widely used method today. In this type of studies, GIS and geo-spatial statistical tools are used to evaluate land units and present the results in suitability maps. The present work aims to characterize the suitability of soils in the province of Catamarca for pecan nut production according to the variables: rockiness, salinity, risk of water-logging, depth, texture and drainage described in the Soil Map of Argentina at a scale of 1:500,000 published by the National Institute of Agricultural Technology. A classification of the suitability of the soil cartographic units was made according to crop requirements, applying the methodology proposed by FAO. The standardization of variables made by omega score and the calculation of the spatial classification score were carried out as a result of the synthesis of the spatial distribution of soil suitability. The applied methodology allowed obtaining the soil suitability map resulting in a total of 60,662 km² suitable for pecan nut production, which accounts for 59.8% of the total area of the province.

In order to optimize the environmental factors for cucumber growth, a fertilizer and water control system was designed based on the Internet of Things (IoT) system. The IoT system monitors environmental factors such as temperature, light and soil Ec value, and uses image processing to obtain four growth indicators such as cucumber stem height, stem diameter size, number of leaves and number of fruit set to establish a single growth indicator model for temperature, light, soil Ec value and growth stage, and the four growth indicators were fused to obtain the comprehensive growth indicator I_c for cucumber, and calculates its deviation to determine the cucumber growth status. Based on the integrated growth index I_c of cucumber, a soil Ec control model was established to provide the optimal environment and fertilizer ration for cucumber at different growth stages to achieve stable and high yield of cucumber.

This study applies machine learning methods such as Decision Tree (CART) and Random Forest to classify drought intensity based on meteorological data. The goal of the study was to evaluate the effectiveness of these methods for drought classification and their use in water resource management and agriculture. The methodology involved using two machine learning models that analyzed temperature and humidity indicators, as well as wind speed indicators. The models were trained and tested on real meteorological data to assess their accuracy and identify key factors affecting predictions. Results showed that the Random Forest model achieved the highest accuracy of 94.4% when analyzing temperature and humidity indicators, while the Decision Tree (CART) achieved an accuracy of 93.2%. When analyzing wind speed indicators, the models’ accuracies were 91.3% and 93.0%, respectively. Feature importance revealed that atmospheric pressure, temperature at 2 m, and wind speed are key factors influencing drought intensity. One of the study’s limitations was the insufficient amount of data for high drought levels (classes 4 and 5), indicating the need for further data collection. The innovation of this study lies in the integration of various meteorological parameters to build drought classification models, achieving high prediction accuracy. Unlike previous studies, our approach demonstrates that using a wide range of meteorological data can significantly improve drought classification accuracy. Significant findings include the necessity to expand the dataset and integrate additional climatic parameters to improve models and enhance their reliability.

The coastal area of Bohai Bay of China has a wide distribution of salt-accumulated soils which could pose a problem to the sustainable development of the local ecology. As a result, the land remains largely degraded and unsuitable for biophysical and agricultural purposes. In this study, we characterized the soil and native plants in the area, to properly understand and identify species with satisfactory adaptation to saline soil and of high economic or ecological value that could be further developed or domesticated, using appropriate cultivation techniques. The goal was to determine the salinity parameters of the soil, identify the inhabiting plant species and contribute to the ecosystem data base for the Bay area. A field survey involving soil and plant sampling and analyses was conducted in Yanshan and Haixing Counties of Hebei Province, China, to estimate the level of salt ions as well as plant species population and type. The mean electrical conductivity (EC) of the soils ranged from 0.47 in more remote locations to 23.8 ds/m in locations closer to the coastline and the total salt ions from 0.05 to 8.8 g/kg, respectively. Each of the salinity parameters, except HCO₃⁻ showed wide variations as judged from the coefficient of variation (CV) values. The EC, as well as chloride, sulphate, Mg and Na ions increased significantly towards the coastline but the HCO₃⁻ ion showed a relatively even distribution across sampling points. Sodium was the most abundant cation and chloride and sulphate the most abundant anions. Therefore, the most dominant salinity-inducing salt that should be properly managed for sustainable ecosystem health was sodium chloride. Based on the EC readings, the most remote location from the coastline was non-saline but otherwise, the salinity ranged from slightly to strongly-very strongly saline towards the coast. There were considerably wide variations in the number and distribution of plant species across sampling locations, but most were dominated entirely Phragmites australis, Setaria viridis and Sueda salsa. Other species identified were Aeluropus littoralis, Chloris virgata, Heteropappus altaicus, Imperata cylindrica, Puccinellia distans, Puccinellia tenuiflora and Scorzonera austriaca. On average, the sampling points furthest from the coast produced the most biomass, and the point with the highest elevation had the most diverse species composition. Among species, Digitaria sanguinalis produced the highest dry mass, followed by Lolium perenne and H. altaicus, but there were considerable variations in biomass yield across sampling locations, with the location nearest the coastline having no vegetation. The observed variations in soil and vegetation should be strongly considered by planners to allow for the sustainable development of the Bahai bay area.

This research delves into the urgent requirement for innovative agricultural methodologies amid growing concerns over sustainable development and food security. By employing machine learning strategies, particularly focusing on non-parametric learning algorithms, we explore the assessment of soil suitability for agricultural use under conditions of drought stress. Through the detailed examination of varied datasets, which include parameters like soil toxicity, terrain characteristics, and quality scores, our study offers new insights into the complexities of predicting soil suitability for crops. Our findings underline the effectiveness of various machine learning models, with the decision tree approach standing out for its accuracy, despite the need for comprehensive data gathering. Moreover, the research emphasizes the promise of merging machine learning techniques with conventional practices in soil science, paving the way for novel contributions to agricultural studies and practical implementations.